uml-mcp

A Python MCP server that generates diagrams (UML via PlantUML and others via Kroki/related renderers) from natural language and/or provided diagram code, exposing tools and resources through MCP and an HTTP endpoint (including a FastAPI app with `/mcp` for hosted use).

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ DevTools mcp uml diagram-generation plantuml kroki mermaid fastapi python
⚙ Agent Friendliness
55
/ 100
Can an agent use this?
🔒 Security
40
/ 100
Is it safe for agents?
⚡ Reliability
40
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
72
Error Messages
0
Auth Simplicity
25
Rate Limits
10

🔒 Security

TLS Enforcement
55
Auth Strength
20
Scope Granularity
10
Dep. Hygiene
65
Secret Handling
60

Security controls (auth, authorization, rate limiting, logging redaction) are not documented in the provided content. The service relies on external renderers (Kroki/PlantUML/Mermaid.ink), which increases exposure to upstream availability and potential data disclosure depending on deployment. TLS is likely available on hosted endpoints (Vercel), but enforcement for self-hosted HTTP is not clearly stated.

⚡ Reliability

Uptime/SLA
10
Version Stability
45
Breaking Changes
30
Error Recovery
75
AF Security Reliability

Best When

You want an MCP-compatible diagram-generation workflow where an agent can call `generate_uml` / `generate_diagram_url` and receive render outputs with fallback across multiple rendering backends.

Avoid When

You need strong, documented security controls for public deployments (auth, rate limiting, data retention) or you cannot rely on third-party rendering endpoints.

Use Cases

  • Generate UML diagrams (class/sequence/activity/use-case/state/component/deployment/object) from descriptions or templates
  • Produce non-UML diagrams via Kroki-compatible backends (Mermaid, D2, Graphviz, TikZ, ERD, BlockDiag, BPMN, C4)
  • Use with AI desktop clients that support MCP (e.g., Cursor, Claude Desktop) to request diagram artifacts (URL/base64/SVG/PNG/PDF/etc.)
  • Convert or render PlantUML/Mermaid-like code into shareable image outputs for documentation

Not For

  • High-assurance/regulated environments needing strict data governance guarantees
  • Use cases requiring complex authentication, tenant isolation, or enterprise audit features (not evidenced)
  • Latency-sensitive workloads if relying on external rendering services (Kroki/PlantUML server/Mermaid.ink) without dedicated infrastructure

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication mechanisms are described in the provided README. The hosted MCP endpoint is mentioned as publicly reachable, which may imply either no auth or auth handled externally by the hosting/MCP client.

Pricing

Free tier: No
Requires CC: No

Pricing is not described for this package itself; rendering may depend on external services (e.g., Kroki/PlantUML/Mermaid.ink) which could introduce usage-based costs depending on deployment.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Rendering backends are external/variable (Kroki first with fallback). Agents should expect occasional failures or slow responses due to upstream services.
  • Some operations may write to disk when `output_dir` is provided; use `generate_diagram_url` to avoid file writes in environments where disk access is restricted.
  • Output format/behavior can vary by diagram type and backend support (e.g., which formats are available).

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for uml-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered